frontend
claudeDomain-modular React apps (Vite, React Router, RTK Query, shadcn/ui, Vitest), with thin architecture adapters for Vue and Angular.
18 skills
Stack-agnostic architecture principles (clean-architecture zones, state, test pyramid), the greenfield kickoff orchestrator, and the adopt-vs-defer decision for existing codebases. Ships SessionStart and PreToolUse hooks.
Plugin architecture-foundations from marketplace kaizen-plugins in kaizenanalytix/kaizen-claude-plugins. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
clean-architectureApplies a framework-agnostic three-zone model (core, modules, shared) for organizing any application's codebase, and enforces a one-way dependency flow between zones so business domains stay decoupled and reusable code stays free of business logic. This skill should be used when the user asks to "st
existing-codebase-adoptionDecides, once and explicitly, whether to impose this suite's conventions for a given discipline on a project that already has its own existing structure, or to defer to that structure instead — then records the decision so later work stays consistent, and keeps handling one-off inconsistencies disco
project-kickoffOrchestrates the start of a brand-new project end to end — asks the shape of the build up front, establishes the design system before any component exists, then routes to the framework bootstrap, the architecture skeleton, the API contract, and finally seeds the codebase-map cache. Writes nothing in
state-philosophyApplies the framework-agnostic distinction between server state (remote data fetched and cached locally, subject to staleness and invalidation) and client/UI state (session-local state genuinely owned by the app), and the general concepts of cache invalidation and optimistic updates. This skill shou
test-pyramidApplies the tooling-agnostic test pyramid — unit, integration, and end-to-end/contract tests — to decide what kind of test a given piece of behavior needs and in what proportion each layer should be written. This skill should be used when the user asks "what should I test", "testing strategy", "test
ui-architectureApplies the three-zone model (core/modules/shared) specifically to a UI application, in framework-neutral terms — no React, Vue, Angular, or any other library vocabulary. Use for a UI codebase whose framework is unknown, not yet chosen, or has no adapter skill in this suite, when the user asks thing
working-agreementHow work gets done regardless of stack: verification is batched and asked for rather than run continuously, pre-existing problems found near a change are surfaced rather than silently fixed, a model tier is recommended at decision points, and no implementation detail is assumed without checking exis
node "${CLAUDE_PLUGIN_ROOT}/scripts/working-agreement.js"
node "${CLAUDE_PLUGIN_ROOT}/scripts/adoption-gate.js"
Domain-modular React apps (Vite, React Router, RTK Query, shadcn/ui, Vitest), with thin architecture adapters for Vue and Angular.
18 skills
Clean-architecture FastAPI backends with testing, bootstrap and best practices, plus thin adapters for Node.js, NestJS, Django and Spring.
13 skills
Analyze & Design phase: business requirements, technical design docs, data models, solution-overview, data-flow, API-sequence and architecture diagrams, plus a build handoff package.
8 skills
The authority layer for technical delivery: previews before destructive or database-writing commands (Bash and PowerShell), a hard scope gate on database file edits only, and a standing block on git commit/push/PR — the agent drafts commit messages and PR descriptions as text, with no AI attribution. Ships SessionStart, UserPromptSubmit, PreToolUse and PostToolUse hooks.
5 skills · hooks
Kvantum Element X pre-load prep: raw client extracts plus template in, validated load-ready file and an input-review dashboard out.
6 skills
Chooses how an app should ship before writing anything: Dockerfiles, CI/CD pipelines, dev/staging/prod config, secrets, and rollback.
5 skills
Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
200 skills · 98 commands · 71 agents · 1 MCP server · hooks
Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin creation and validation.
7 skills · 1 command · 3 agents
CMEM Pro for the Claude app - hooks stream tool use to cmem.ai and inject observations into new sessions and agents
3 skills · 1 MCP server · hooks
AI-powered codebase understanding — analyze, visualize, and explain any project
9 skills · 10 agents · hooks
Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data
9 skills · 9 commands · 11 agents · 1 MCP server
Headroom startup hooks for Claude Code and GitHub Copilot CLI.
hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.